INDEX

Explanations

fundamentals

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-sdk

-0.28

UBL

-0.27

entials

-0.26

-stream

-0.26

Ub

-0.25

 Browse

-0.25

Browse

-0.25

erot

-0.25

 Filed

-0.24

sss

-0.23

POSITIVE LOGITS

éĻĢ

0.30

mare

0.29

<src

0.28

Pic

0.27

acht

0.27

amic

0.26

pic

0.26

rese

0.26

ptic

0.26

bine

0.26

Activations Density 0.002%

fundamentals

No Comments

No Known Activations